Stable Diffusion XL - Image Text Editor

Transform and enhance your images using natural language descriptions with Stability AI's powerful Stable Diffusion XL model. This advanced text-based image editor allows you to modify existing images by describing the changes you want to see, from subtle style adjustments to dramatic transformations.

Endpoint

POSThttps://api.1min.ai/api/features

Request Headers

Field	Value
API-KEY	<api-key>
Content-Type	application/json

Parameters

Parameter	Type	Required	Description
type	string	Yes	Feature type identifier. Must be IMAGE_EDITOR
model	string	Yes	AI model identifier. Must be stable-diffusion-xl-1024-v1-0
promptObject	object	Yes	Configuration object containing all image editing parameters

Prompt Object Parameters

Parameter	Type	Required	Description	Default
imageUrl	string	Yes	Path to the source image to be edited	-
prompt	string	Yes	Text description of the desired image transformation	-
samples	number	Yes	Number of outputs	1
cfg_scale	number	No	Configuration scale for prompt adherence (0-35)	7
steps	number	No	Number of inference steps (10-50)	30
seed	number	No	Random seed for reproducibility (0-4294967295)	0
clip_guidance_preset	string	No	CLIP guidance preset for style consistency	NONE
image_strength	number	No	Strength of original image influence (0-1)	0.35
step_schedule_start	number	No	Starting point in diffusion process (0.0-1.0)	0.65
step_schedule_end	number	No	Ending point in diffusion process (0.0-1.0)	auto
sampler	string	No	Sampling algorithm to use	auto
style_preset	string	No	Predefined style to apply	auto

CLIP Guidance Presets

Preset	Description
NONE	No additional guidance (fastest processing)
FAST_BLUE	Fast processing with blue color emphasis
FAST_GREEN	Fast processing with green color emphasis
SIMPLE	Basic guidance for improved coherence
SLOW	Detailed guidance for maximum quality
SLOWER	Most detailed guidance (longest processing)
SLOWEST	Maximum quality guidance

Sampler Options

Sampler	Description
DDIM	Denoising Diffusion Implicit Models
DDPM	Denoising Diffusion Probabilistic Models
K_DPMPP_2M	DPM++ 2M Karras scheduler
K_DPMPP_2S_ANCESTRAL	DPM++ 2S Ancestral scheduler
K_DPM_2	DPM 2 scheduler
K_DPM_2_ANCESTRAL	DPM 2 Ancestral scheduler
K_EULER	Euler scheduler
K_EULER_ANCESTRAL	Euler Ancestral scheduler
K_HEUN	Heun scheduler
K_LMS	Linear multistep scheduler

Style Presets

Style	Description
3d-model	Three-dimensional modeling style
analog-film	Vintage analog film aesthetic
anime	Japanese anime and manga style
cinematic	Movie and film-like quality
comic-book	Comic book illustration style
digital-art	Modern digital artwork style
enhance	General enhancement and improvement
fantasy-art	Fantasy and magical themes
line-art	Clean line art and illustrations
low-poly	Low polygon 3D style
modeling-compound	Clay modeling appearance
neon-punk	Cyberpunk with neon aesthetics
origami	Paper folding art style
photographic	Realistic photographic style
pixel-art	Retro pixel art style
tile-texture	Seamless texture patterns

Code Examples

cURL

curl -X POST "https://api.1min.ai/api/features" \
-H "API-KEY: <api-key>" \
-H "Content-Type: application/json" \
-d '{
  "type": "IMAGE_EDITOR",
  "model": "stable-diffusion-xl-1024-v1-0",
  "promptObject": {
    "imageUrl": "development/images/2025_02_16_15_42_40_711_human.jpg",
    "prompt": "transform into a watercolor painting style with soft brushstrokes and vibrant colors",
    "samples": 1,
    "cfg_scale": 8,
    "steps": 50,
    "seed": 42,
    "clip_guidance_preset": "SIMPLE",
    "image_strength": 0.4,
    "step_schedule_start": 0.65,
    "step_schedule_end": 0.01,
    "sampler": "K_DPMPP_2M",
    "style_preset": "digital-art"
  }
}'

JavaScript

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'IMAGE_EDITOR',
  model: 'stable-diffusion-xl-1024-v1-0',
  promptObject: {
    imageUrl: 'development/images/2025_02_16_15_42_40_711_human.jpg',
    prompt: 'transform into a watercolor painting style with soft brushstrokes and vibrant colors',
    samples: 1,
    isMasked: false,
    cfg_scale: 8,
    clip_guidance_preset: 'SIMPLE',
    image_strength: 0.4,
    seed: 42,
    step_schedule_start: 0.65,
    steps: 50
  }
})
})

Python

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

data = {
"type": "IMAGE_EDITOR",
"model": "stable-diffusion-xl-1024-v1-0",
"promptObject": {
  "imageUrl": "development/images/2025_02_16_15_42_40_711_human.jpg",
  "prompt": "transform into a watercolor painting style with soft brushstrokes and vibrant colors",
  "samples": 1,
  "isMasked": False,
  "cfg_scale": 8,
  "clip_guidance_preset": "SIMPLE",
  "image_strength": 0.4,
  "seed": 42,
  "step_schedule_start": 0.65,
  "steps": 50
}
}

response = requests.post(url, headers=headers, json=data)

Interactive Playground

API Playground

GETPOSTPUTDELETEhttps://api.1min.ai/api/features

AI Model *Stable Diffusion XL

Image URL *

Path to the source image to be edited

Prompt *

Describe the transformation you want to apply

transform into a watercolor painting style with soft brushstrokes and vibrant colors

CFG Scale

Configuration scale for prompt adherence (0-35)

Steps

Number of inference steps (10-50)

Seed

Random seed for reproducibility (0-4294967295)

CLIP Guidance Preset

CLIP guidance preset for style consistency

NONEFAST_BLUEFAST_GREENSIMPLESLOWSLOWERSLOWEST

Image Strength

Original image influence (0-1, lower = more change)

Step Schedule Start

Starting point in diffusion process (0.0-1.0)

Step Schedule End

Ending point in diffusion process (0.0-1.0)

Sampler

Sampling algorithm to use

DDIMDDPMK_DPMPP_2MK_DPMPP_2S_ANCESTRALK_DPM_2K_DPM_2_ANCESTRALK_EULERK_EULER_ANCESTRALK_HEUNK_LMS

Style Preset

Predefined style to apply

3d-modelanalog-filmanimecinematiccomic-bookdigital-artenhancefantasy-artline-artlow-polymodeling-compoundneon-punkorigamiphotographicpixel-arttile-texture

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "IMAGE_EDITOR",
  "model": "stable-diffusion-xl-1024-v1-0",
  "promptObject": {
    "imageUrl": "development/images/2025_02_16_15_42_40_711_human.jpg",
    "prompt": "transform into a watercolor painting style with soft brushstrokes and vibrant colors",
    "cfg_scale": 8,
    "steps": 50,
    "seed": 42,
    "clip_guidance_preset": "SIMPLE",
    "image_strength": 0.4,
    "step_schedule_start": 0.65,
    "step_schedule_end": 0.01,
    "sampler": "K_DPMPP_2M",
    "samples": 1,
    "style_preset": "digital-art"
  }
}'

Response Format

{
"aiRecord": {
  "uuid": "e8e3d645-d5a4-4c18-975b-95395d3b49e1",
  "userId": "c937fbcc-fa8f-4565-a440-c4d87f56fcb2",
  "teamId": "a4e176b2-dabb-451e-9c58-62b451fa9630",
  "model": "stable-diffusion-xl-1024-v1-0",
  "type": "IMAGE_EDITOR",
  "status": "SUCCESS",
  "createdAt": "2025-10-24T08:00:44.752Z",
  "aiRecordDetail": {
    "promptObject": {
      "imageUrl": "development/images/2025_02_16_15_42_40_711_human.jpg",
      "prompt": "transform into a watercolor painting style with soft brushstrokes and vibrant colors",
      "cfg_scale": 8,
      "steps": 50,
      "seed": 42,
      "clip_guidance_preset": "SIMPLE",
      "image_strength": 0.4,
      "step_schedule_start": 0.65,
      "step_schedule_end": 0.01,
      "sampler": "K_DPMPP_2M",
      "samples": 1,
      "style_preset": "digital-art"
    },
    "resultObject": [
      "development/images/2025_10_24_15_00_52_401_480067.jpg"
    ]
  },
  "temporaryUrl": "https://s3.us-east-1.amazonaws.com/asset.1min.ai/development/images/2025_10_24_15_00_52_401_480067.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256..."
}
}

Use Cases

• Style Transfer: Transform photos into artistic styles (watercolor, oil painting, sketch)
• Mood Enhancement: Adjust lighting, atmosphere, and emotional tone
• Creative Photography: Season changes, genre switching, artistic effects
• Commercial Content: Product visualization, brand adaptation, marketing materials
• Digital Art: Concept development, character design, environment creation

Tips for Best Results

1. Image Strength Settings:

   • Use 0.2-0.4 for dramatic style changes
   • Use 0.5-0.7 for moderate adjustments
   • Use 0.8-1.0 for subtle enhancements

2. Quality Optimization:

   • Use 30-50 steps for high quality
   • Higher CFG scale for more prompt adherence
   • SLOW/SLOWER presets for professional work

3. Prompt Guidelines:

   • Be specific about style and technique
   • Include lighting and mood descriptions
   • Use artistic terminology for better results

Content Guidelines

All generated content is subject to safety filters and content policies.